Audio-Video Biometric System with Liveness Checks

Girija Chetty, Michael Wagner

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract


    In this paper we propose multimodal fusion of super resolved texture (SRT) features and 3D shape features
    with acoustic features for 3D audio-video person authentication systems with liveness checks. The proposed SRT
    features allow information related to non-rigid variations on speaking faces, such as expression lines, gestures,
    and wrinkles, enhancing the performance of the system against impostor and spoof attacks. Experiments with
    multimodal fusion of acoustic and super-resolved texture and 3D shape features for two different speaking face
    data corpus, VidTIMIT, and AVOZES, allowed equal error rates (EERs) of less than 0.5 % for imposter and
    type-1 replay attacks (still photo and pre-recorded audio) and less than 3% for more complex type-2 replay
    attacks (pre-recorded video or fake CG animated video).
    Original languageEnglish
    Title of host publicationProceedings of the Conference on Image and Vision Computing - New Zealand
    EditorsBrendan McCane
    Place of PublicationNew Zealand
    PublisherUniversity of Otago, Dunedin, New Zealand.
    Pages132-137
    Number of pages6
    ISBN (Print)00473105233
    Publication statusPublished - 2005
    EventIVCNZ-2005 - Dunedin, New Zealand
    Duration: 28 Nov 200529 Nov 2005

    Conference

    ConferenceIVCNZ-2005
    CountryNew Zealand
    CityDunedin
    Period28/11/0529/11/05

    Fingerprint

    Biometrics
    Fusion reactions
    Textures
    Acoustics
    Authentication
    Experiments

    Cite this

    Chetty, G., & Wagner, M. (2005). Audio-Video Biometric System with Liveness Checks. In B. McCane (Ed.), Proceedings of the Conference on Image and Vision Computing - New Zealand (pp. 132-137). New Zealand: University of Otago, Dunedin, New Zealand..
    Chetty, Girija ; Wagner, Michael. / Audio-Video Biometric System with Liveness Checks. Proceedings of the Conference on Image and Vision Computing - New Zealand. editor / Brendan McCane. New Zealand : University of Otago, Dunedin, New Zealand., 2005. pp. 132-137
    @inproceedings{5389e97b52644466ae32efc9a1120f42,
    title = "Audio-Video Biometric System with Liveness Checks",
    abstract = "In this paper we propose multimodal fusion of super resolved texture (SRT) features and 3D shape featureswith acoustic features for 3D audio-video person authentication systems with liveness checks. The proposed SRTfeatures allow information related to non-rigid variations on speaking faces, such as expression lines, gestures,and wrinkles, enhancing the performance of the system against impostor and spoof attacks. Experiments withmultimodal fusion of acoustic and super-resolved texture and 3D shape features for two different speaking facedata corpus, VidTIMIT, and AVOZES, allowed equal error rates (EERs) of less than 0.5 {\%} for imposter andtype-1 replay attacks (still photo and pre-recorded audio) and less than 3{\%} for more complex type-2 replayattacks (pre-recorded video or fake CG animated video).",
    author = "Girija Chetty and Michael Wagner",
    year = "2005",
    language = "English",
    isbn = "00473105233",
    pages = "132--137",
    editor = "Brendan McCane",
    booktitle = "Proceedings of the Conference on Image and Vision Computing - New Zealand",
    publisher = "University of Otago, Dunedin, New Zealand.",

    }

    Chetty, G & Wagner, M 2005, Audio-Video Biometric System with Liveness Checks. in B McCane (ed.), Proceedings of the Conference on Image and Vision Computing - New Zealand. University of Otago, Dunedin, New Zealand., New Zealand, pp. 132-137, IVCNZ-2005, Dunedin, New Zealand, 28/11/05.

    Audio-Video Biometric System with Liveness Checks. / Chetty, Girija; Wagner, Michael.

    Proceedings of the Conference on Image and Vision Computing - New Zealand. ed. / Brendan McCane. New Zealand : University of Otago, Dunedin, New Zealand., 2005. p. 132-137.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Audio-Video Biometric System with Liveness Checks

    AU - Chetty, Girija

    AU - Wagner, Michael

    PY - 2005

    Y1 - 2005

    N2 - In this paper we propose multimodal fusion of super resolved texture (SRT) features and 3D shape featureswith acoustic features for 3D audio-video person authentication systems with liveness checks. The proposed SRTfeatures allow information related to non-rigid variations on speaking faces, such as expression lines, gestures,and wrinkles, enhancing the performance of the system against impostor and spoof attacks. Experiments withmultimodal fusion of acoustic and super-resolved texture and 3D shape features for two different speaking facedata corpus, VidTIMIT, and AVOZES, allowed equal error rates (EERs) of less than 0.5 % for imposter andtype-1 replay attacks (still photo and pre-recorded audio) and less than 3% for more complex type-2 replayattacks (pre-recorded video or fake CG animated video).

    AB - In this paper we propose multimodal fusion of super resolved texture (SRT) features and 3D shape featureswith acoustic features for 3D audio-video person authentication systems with liveness checks. The proposed SRTfeatures allow information related to non-rigid variations on speaking faces, such as expression lines, gestures,and wrinkles, enhancing the performance of the system against impostor and spoof attacks. Experiments withmultimodal fusion of acoustic and super-resolved texture and 3D shape features for two different speaking facedata corpus, VidTIMIT, and AVOZES, allowed equal error rates (EERs) of less than 0.5 % for imposter andtype-1 replay attacks (still photo and pre-recorded audio) and less than 3% for more complex type-2 replayattacks (pre-recorded video or fake CG animated video).

    M3 - Conference contribution

    SN - 00473105233

    SP - 132

    EP - 137

    BT - Proceedings of the Conference on Image and Vision Computing - New Zealand

    A2 - McCane, Brendan

    PB - University of Otago, Dunedin, New Zealand.

    CY - New Zealand

    ER -

    Chetty G, Wagner M. Audio-Video Biometric System with Liveness Checks. In McCane B, editor, Proceedings of the Conference on Image and Vision Computing - New Zealand. New Zealand: University of Otago, Dunedin, New Zealand. 2005. p. 132-137